End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: Qwen/Qwen3-1.7B
+datasets: atomwalk12/linalgzero-distilled-debug
 library_name: transformers
 model_name: Qwen3-1.7B-Instruct-SFT
 tags:
 - generated_from_trainer
 - trl
+- tool-use
+- linalg-zero
 - sft
 licence: license
 ---
 
 # Model Card for Qwen3-1.7B-Instruct-SFT
 
-This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
+This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on the [atomwalk12/linalgzero-distilled-debug](https://huggingface.co/datasets/atomwalk12/linalgzero-distilled-debug) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.903278112411499,
+    "eval_runtime": 1.4988,
+    "eval_samples": 4,
+    "eval_samples_per_second": 2.669,
+    "eval_steps_per_second": 2.669,
     "total_flos": 952828382195712.0,
     "train_loss": 0.0,
     "train_runtime": 6.839,

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.903278112411499,
+    "eval_runtime": 1.4988,
+    "eval_samples": 4,
+    "eval_samples_per_second": 2.669,
+    "eval_steps_per_second": 2.669
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
-size 11422654
+oid sha256:dc68ef9483e17b8453514159d4e669d963d343267a9407d51bfe1a5c3d81e7a3
+size 11422755